• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.840-860
• /
• 2023

Aiming at the serious occlusion and slow tracking speed in pedestrian target tracking and recognition in complex scenes, a target tracking method based on improved YOLO v5 combined with Deep SORT is proposed. By merging the attention mechanism ECA-Net with the Neck part of the YOLO v5 network, using the CIoU loss function and the method of CIoU non-maximum value suppression, connecting the Deep SORT model using Shuffle Net V2 as the appearance feature extraction network to achieve lightweight and fast speed tracking and the purpose of improving tracking under occlusion. A large number of experiments show that the improved YOLO v5 increases the average precision by 1.3% compared with other algorithms. The improved tracking model, MOTA reaches 54.3% on the MOT17 pedestrian tracking data, and the tracking accuracy is 3.7% higher than the related algorithms and The model presented in this paper improves the FPS by nearly 5 on the fps indicator.

• Journal of the Korean Applied Science and Technology
• /
• v.37 no.4
• /
• pp.1020-1033
• /
• 2020

This study attempted to investigate the usefulness of Rhus javanica L., Cinnamomum verum and Rosmarinus officinalis extracts which have antimicrobial and antioxidant effects without any harm on human health as natural preservatives. In terms of extraction, extraction by 70% ethanol and hot-water extraction were used for Cinnamomum verum and Rhus javanica L. respectively. For Rosmarinus officinalis, a mixed method (70% ethanol and hot-water extraction) was adopted. In terms of experimental methods, antimicrobial effects, antioxidant activity through DPPH and safety and stability of cosmetics were assessed, and a challenge test was performed, and the results found the followings: According to an antimicrobial test, good antimicrobial effects were found in bacteria (Rhus javanica L. extract) and fungi (Cinnamomum verum extract). In contrast, the Rosmarinus officinalis extract was set aside because of poor antimicrobial activity. In the mixed extract (Rhus javanica L. + Cinnamomum verum), antimicrobial effects were observed in 'complex C (mixed in a 1:1 ratio)' while both inhibitory and sterilizing effects were found in 5 different test strains at minimum inhibitory concentration (MIC) and minimum bactericidal concentration (MBC). In addition, antioxidant effects were detected in non-mixed extract and mixed extract ('complex C'). Furthermore, a test on cosmetics which adopted '10% complex C' instead of synthetic preservative revealed safety and stability. Therefore, this study has confirmed the potential of the Rhus javanica L., Cinnamomum verum and Rosmarinus officinalis extracts as materials for natural preservatives.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.754-758
• /
• 2009

Extracting information in large-scale documents would be very useful not only for information retrieval but also for question answering and summarization. Even though relation extraction is very important area, it is difficult to develop and evaluate a machine learning based system without test collection. The study shows how to build test collection(KREC2008) for the relation extraction system. We extracted technology terms from abstracts of journals and selected several relation candidates between them using Wordnet. Judges who were well trained in evaluation process assigned a relation from candidates. The process provides the method with which even non-experts are able to build test collection easily. KREC2008 are open to the public for researchers and developers and will be utilized for development and evaluation of relation extraction system.

• Korean Journal of Plant Resources
• /
• v.24 no.5
• /
• pp.499-506
• /
• 2011

The purpose of this study was to search available resources for new natural colorants. The extraction efficiency of colorants from black cowpea seed coats and their storage stability were examined according to the various extraction and storage conditions in this study. The results obtained were as follows: the optical density (O.D.) values of the extracted colorants increased with increasing extract time and temperature. Extraction at pH 4 was seen to be the most efficient among the various pH conditions. The color of the extract solutions were seen to change with variation in pH, for example, anthocyanins display color changes from orange-red, to orange, to blue, to greenish-blue at pH 3.0, 4.0-6.0, 7.0 and 9.0-11.0, respectively. The color changes of the extract solutions over various storage periods were determined using UV/Vis spectra these color changes indicate characteristic absorption patterns and a discoloration index which indicates the rate of absorbance (532 nm/454 nm). Methionine addition influenced the storage stability of the colorant solutions and this addition led to better storage stability than non-addition. In paper chromatography of juice extracted colorant, a long stripe was seen on development. Among three colorants obtained via paper chromatography according to development rate, at least two different colorants were mixed indicated by the appearance, or not, of a shoulder at 552 nm depending on the extent of development.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.7
• /
• pp.23-35
• /
• 2013

This paper proposes an effective technique that is used to automatically extract feature vectors from vibration signals for fault classification systems. Conventional mel-frequency cepstral coefficients (MFCCs) are sensitive to noise of vibration signals, degrading classification accuracy. To solve this problem, this paper proposes spectral envelope cepstral coefficients (SECC) analysis, where a 4-step filter bank based on spectral envelopes of vibration signals is used: (1) a linear predictive coding (LPC) algorithm is used to specify spectral envelopes of all faulty vibration signals, (2) all envelopes are averaged to get general spectral shape, (3) a gradient descent method is used to find extremes of the average envelope and its frequencies, (4) a non-overlapped filter is used to have centers calculated from distances between valley frequencies of the envelope. This 4-step filter bank is then used in cepstral coefficients computation to extract feature vectors. Finally, a multi-layer support vector machine (MLSVM) with various sigma values uses these special parameters to identify faulty types of induction motors. Experimental results indicate that the proposed extraction method outperforms other feature extraction algorithms, yielding more than about 99.65% of classification accuracy.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.5
• /
• pp.183-191
• /
• 2010

Unique and invariant biometric characteristics have been used for secure user authentication. Storing original biometric data is not acceptable due to privacy and security concerns of biometric technology. In order to enhance the security of the biometric data, the cancelable biometrics was introduced. Using revocable and non-invertible transformation, the cancelable biometrics can provide a way of more secure biometric authentication. In this paper, we present a new cancelable bits extraction method for the facial data. For the feature extraction, the Subpattern-based Principle Component Analysis (PCA) is adopted. The Subpattern-based PCA divides a whole image into a set of partitioned subpatterns and extracts principle components from each subpattern area. The feature extracted by using Subpattern-based PCA is discretized with a helper data based method. The elements of the obtained bits are evaluated and ordered according to a measure based on the fisher criterion. Finally, the most discriminative bits are chosen as the biometric bits string and used for authentication of each identity. Even if the generated bits string is compromised, new bits string can be generated simply by changing the helper data. Because, the helper data utilizes partial information of the feature, the proposed method does not reveal privacy sensitive biometric information of the user. For a security evaluation of the proposed method, a scenario in which the helper is compromised by an adversary is also considered.

• Korean Journal of Remote Sensing
• /
• v.32 no.5
• /
• pp.471-482
• /
• 2016

This paper presents an extraction method for water body which uses block-based image partitioning and extension of water body boundaries to improve the performance of supervised classification for water body extraction. The Mahalanobis distance image is created by computing the spectral information of Normalized Difference Water Index (NDWI) and Near Infrared (NIR) band images over a training site within the water body in order to extract an initial water body area. To reduce the effect of noise contained in the Mahalanobis distance image, we apply mean curvature diffusion to the image, which controls diffusion coefficients based on connectivity strength between adjacent pixels and then extract the initial water body area. After partitioning the extracted water body image into the non-overlapping blocks of same size, we update the water body area using the information of water body belonging to water body boundaries. The update is performed repeatedly under the condition that the statistical distance between water body area belonging to water body boundaries and the training site is not greater than a threshold value. The accuracy assessment of the proposed algorithm was tested using KOMPSAT-2 images for the various block sizes between $11{\times}11$ and $19{\times}19$. The overall accuracy and Kappa coefficient of the algorithm varied from 99.47% to 99.53% and from 95.07% to 95.80%, respectively.

• Food Science and Preservation
• /
• v.23 no.1
• /
• pp.20-26
• /
• 2016

In this study, the anti-inflammatory effect of hyaluronidase (HAase) inhibition was determined from 92 species of oriental herbal medicine extracted with water and ethanol solvents because of their non-toxicity in the human body. The water extracts of Evodia officinalis (86.8%), Thuja orientalis (80.8%), Carthami semen (66.5%), Melia azedarach (74.7%), Siegesbeckia pubescens (61.3%), Saururus chinensis (49.15%) showed a relatively greater anti-inflammatory activity. The ethanol extracts of Ailanthus altissima and Saururus chinensis demonstrated the highest anti-inflammatory effect at above 90%. Saururus chinensis was selected for its high anti-inflammatory effect in both water and ethanol extract. Ethanol was more effective than water and optimal extraction conditions for phenolic compounds was determined to be extraction with 50% ethanol for 12 hours. The extracts from Saururus chinensis in optimal condition showed 70~80% anti-inflammatory effect when $100{\sim}250{\mu}g/mL$ phenolic concentration was treated. Concentration of above $500{\mu}g/mL$ decreased the inhibitory effect. The anti-inflammatory effect and extraction yield were increased by ultra-fine grind technology, indicating that this method can be used to increase the extraction yield of phenolic compounds from medicinal plants.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.40 no.5
• /
• pp.712-716
• /
• 2011

We investigated changes in the extraction yield and whitening activity of polysaccharides from Undaria pinnatifida sporophyll due to gamma irradiation. U. pinnatifida sporophyll was gamma-irradiated at doses of 10, 30, 50, 70, and 100 kGy, then extracted with hot water and precipitated with ethanol to extract polysaccharides. Crude polysaccharide yields increased with an increase in irradiation dosage, but tyrosinase inhibition activity did not change. Melanin synthesis did not significantly differ between B16BL6 cells treated with irradiated and non-irradiated samples. In conclusion, gamma irradiation increased the crude polysaccharide extraction yield but did not change the whitening activity of U. pinnatifida sporophyll. This implies that gamma irradiation can be used to increase yields in the cosmetic industry, thus increasing profits.

• Food Science and Preservation
• /
• v.24 no.6
• /
• pp.871-878
• /
• 2017

The objective of this study was to compare antioxidant activities of green tea, rosemary, lemon and bamboo leaves extracts using three different extraction methods (80% ethanol sonication extraction, distilled water autoclave extraction, distilled water extraction at room temperature). As a result, green tea and rosemary extracts showed relatively high antioxidant activities compared with those of lemon and bamboo leaves. These green tea and rosemary extracts were subsequently added to soymilk and their mixtures were examined for antioxidant activities. Soymilk added with 10% green tea distilled water autoclave extracts and distilled water at room temperature extracts showed relatively high DPPH, $85.09{\pm}2.26%$, $84.38{\pm}1.97%$, and ABTS radical scavenging activities, $73.43{\pm}2.78%$, $81.34{\pm}4.78%$, respectively. On the other hand, soymilk added with 10% rosemary distilled water autoclave extracts showed remarkably higher DPPH radical scavenging activity while their ABTS radical scavenging ability was similar to that of non-added soymilk. In conclusion, our results suggest that the addition of green tea distilled water autoclave extracts, distilled water at room temperature extracts and rosemary distilled water autoclave extracts to soymilk could contribute to the development of added value soymilk products with increased antioxidant activities.